Page tree

The AI and ML Showcase has now concluded. Recordings of the event can be viewed below.

13 May 2021

12:00pm – 4pm (AEST) / 10:00am - 2pm (AWST) / 4:00am - 8am (CEST) / 7:00pm - 11pm, (12 May PDT) 

About the Showcase

Four peak presentations will showcase state-of-the-art research aimed at speeding up materials design and discovery by integrating artificial intelligence (AI) and machine learning (ML) techniques. Australian and international speakers reveal how large, high quality datasets coupled with machine learning analysis algorithms can play a vital role in the process of new materials discovery. The presentations will be of broad interest for scientists working in the field of HPC/Big Data in materials design and discovery, from advanced graduate research student level, to early career researchers and beyond.

The recording of the showcase is available on NCI's YouTube Channel

Plenary Speakers

Prof Kristin Persson, UC Berkeley

Kristin Persson is a Professor in Materials Science and Engineering at UC Berkeley with a joint appointment as Senior Faculty Scientist at the Lawrence Berkeley National Laboratory where she serves as Director of the Molecular Foundry. Her expertise is materials informatics, specifically pursuing novel and optimized materials for energy storage applications. She has published more than 200 papers in peer-reviewed journals, holds several patents in energy storage, and is among the world’s 1% most cited researchers. She is most known for her stewardship of the Materials Project (; one of the most visible of the Materials Genome initiative (MGI) funded programs attracting >150,000 users worldwide with more than 3,000 unique users accessing the site every day. She is a leader in the MGI community, and she serves as an Associate Editor for Chemistry of Materials, on the NSF Advisory Committee for Cyberinfrastructure, on the MRS Program Development Subcommittee and is the appointed MGI ambassador for The Metal, Minerals, and Materials Society (TMS). She has received the 2018 DOE Secretary of Energy’s Achievement Award, the 2017 TMS Faculty Early Career Award, the 2020 Falling Walls Science and Innovation Management Award,  the LBNL Director’s award for Exceptional Scientific Achievement (2013) and she is a 2018 Kavli Fellow.

Data-Driven Materials Innovation and Design; Examples from the Materials Project

Fueled by our abilities to compute materials properties and characteristics orders of magnitude faster than they can be measured and recent advancements in harnessing literature data, we are entering the era of the fourth paradigm of science: data-driven materials design. The Materials Project uses supercomputing together with state-of-the-art quantum mechanical theory to compute the properties of all known inorganic materials and beyond, design novel materials and offer the data for free to the community together with online analysis and design algorithms. Currently, the Project contains data derived from quantum mechanical calculations for over 130,000 materials and millions of properties. The resource supports a growing community of data-rich materials research, currently supporting over 160,000 registered users and over 2 million data records served each day through the API. The software infrastructure enables thousands of calculations per week – enabling screening and predictions - for both novel solid as well as molecular species with target properties.  However, truly accelerating materials innovation also requires rapid synthesis, testing and feedback. The ability to devise data-driven methodologies to guide synthesis efforts is needed as well as rapid interrogation and recording of results – including ‘non-successful’ ones. In this talk, I will highlight some of our ongoing work, including new materials development, synthesis and characterization and associated machine learning algorithmic tools and data-driven approaches.

Prof Shyue Ping Ong, UC San Diego, Jacobs School of Engineering

Dr Shyue Ping Ong is an Associate Professor of NanoEngineering at the University of California, San Diego. He obtained his PhD from the Massachusetts Institute of Technology in 2011. His group, the Materials Virtual Lab, is dedicated to the interdisciplinary application of machine learning and first principles computations to accelerate materials design. He is a founding developer of the Materials Project and the globally-used Python Materials Genomics (pymatgen) materials library. Dr Ong is also a recipient of the US Department of Energy Early Career Research Program and the Office of Naval Research Young Investigator Program awards. 

Accelerating Materials Design through Automation and Machine Learning

Machine learning (ML) models have demonstrated human, or even superhuman, performance in many tasks, from playing traditional board games to image classification. Here, I will discuss how ML is poised to have a similar transformative impact in materials science. Applied on large data sets, ML techniques can be used to discover novel technological materials, to model complex systems at an accuracy beyond the reach of traditional computational techniques, and to enhance the accuracy and speed of interpreting characterization data. A key focus of this talk will be on the heterogeneity and scarcity of materials data, the challenges these characteristics present for ML and the potential approaches to overcome them.

Prof Amanda Barnard, Australian National University

Prof. Dr. Amanda Barnard is a Senior Professor at the School of Computing in the Australian National University, the Leader of the Computational Science cluster and the Deputy Director. She received her PhD in theoretical condensed matter physics in 2003 from RMIT University, and is a Fellow of the Australian Institute of Physics and the Royal Society of Chemistry (UK). She currently leads research at the interface of computational modelling, high performance supercomputing, and applied machine learning and artificial intelligence (AI), in target domains of materials science, chemistry and nanotechnology.  Her research has been awarded in 12 national and international awards in 5 scientific disciplines, including the Feynman Prize (Theory) in 2014. She is a leader in the Australasian high performance computing community, and currently serves on the Pawsey Supercomputing Exascale Readiness (PaCER) programme committee, is Chair of the Australasian Leadership Computing Grants Scheme at the National Computational Infrastructure (NCI) and the independent director on the Board of Directors for New Zealand eScience Infrastructure (NeSI).

Classification, Correlation and Causation of Defects in Graphene Oxide Nanomaterials

Materials informatics, and the associated field of nanoinformatics, offer a plethora of new approaches to solving existing challenges in (nano)materials design. These enabling technologies leverage over 50 years of innovation in computer science on machine learning algorithms, and an even longer history of research in statistics to underpin the essential preliminary data science. Provided sufficient appropriate data is available to describe the material or system, new insights can be gained that would be otherwise obscured using conventional experimental or computational methods. Hidden structure/property relationships we can use to inform further research and materials development. Extracting useful insights (such as structure/property relationships) from data analytics and machine learning is however more complicated than simply gathering data and training models, since not all methods are interpretable, and interpretability is essential for decision making. Correlation is also different to causation, and so the importance relationships identified using many machine learning methods are not always actionable. In this presentation we will discuss the differences between conventional modelling approaches and machine learning and demonstrate the advantages of combining a series of different machine learning methods to uncover useful relationships between the properties, structure and processing conditions of graphene oxide nanoflakes.

Prof Nicola Marzari, École Polytechnique fédérale de Lausanne (EPFL)

Nicola Marzari holds the Chair of Theory and Simulation of Materials at the École Polytechnique Fédérale de Lausanne, where he is also the director of the MARVEL National Centre for Computational Design and Discovery of Novel Materials. He also currently holds an Excellence Chair at the University of Bremen. Previous appointments include the Toyota Chair for Materials Processing at the Massachusetts Institute of Technology, and the Statutory Chair of Materials Modelling at the University of Oxford, where he directed the Materials Modelling Laboratory.

The great acceleration in the design and discovery of novel materials

Materials are at the core of our technological advances, and are needed to address many of our societal challenges: from energy to information, from food to medicine. I’ll highlight the great strides made in the last few years in the design and discovery of novel materials, where computational simulations can now precede, streamline, or accelerate experiments. This acceleration is driven by the central paradigm of computational science (doubling performance every 14-16 months), combined with powerful and predictive quantum simulation techniques, and by the convergence of data mining and machine learning towards materials simulations. I'll also underscore the IT requirements needed to perform calculations in a reproducible, shareable, high-throughput mode. A case study will be our computational exfoliation of all known inorganic materials, leading to ~3,000 promising candidates, for which I will discuss some highlights for quantum spin Hall insulators and superconductors.


12:00-12.05Opening Remarks
12.05-12.55Prof Kristin Persson
12.55-13.00Question Time
13.00-13.50Prof Shyue Ping Ong
13.50-13.55Question Time
14.00-14.50Prof Amanda Barnard
14.50-14.55Question Time
15.00-15.50Prof Nicola Marzari
15.50-16:00Question Time


Click here to register on the Zoom registration page.

Chair: Prof Michelle Spencer (RMIT)


Dr. Meiyun Chang-Smith (Graduate Education Program Manager, Intersect)


Dr. Jingbo Wang (Training Manager, NCI)



Prof Michelle Spencer (RMIT)

Professor Michelle Spencer is the Associate Dean of Applied Chemistry & Environmental Science at RMIT University, and leader of the computational materials group. She was awarded her PhD from La Trobe University and is a Fellow of the Royal Australian Chemical Institute (RACI). Her research focuses on using quantum mechanical calculations and ab initio molecular dynamics simulations to develop new materials for electronic devices, sensors and battery applications. She is an Associate Investigator in the Australian Research Council (ARC) Centre of Excellence in Future Low-Energy Electronics Technologies and is a CI on grants awarded from the ARC, the Australian Renewable Energy Agency, the Commonwealth Scientific and Industrial Research Organisation, and the Australian Defense Science & Technology Group.

Recorded Videos

Click the links below to watch the presentations from the recent AI and ML Showcase:

Prof Kristin Persson:

Prof Shyue Ping Ong:

Prof Nicola Marzari:

Click below to download the event's flyer.

  • No labels